Not reviewed
No score, grade or rank. This listing is facts from the official MCP registry and our own checks, and it stays out of the rankings until the panel reviews it.
Search peer-reviewed papers and research methodology guidance from your AI agent.
Facts
- MCP registry
com.luneresearch/lune· 3.0.1- Endpoint
https://mcp.luneresearch.com- Packages
npm@retrograde-labs/lune-mcp-server stdio- Website
- luneresearch.com
- npm / week
- 147
- GitHub stars
- 4
- Registry entry
- updated 5 Nov 2026
From the official MCP registry, the package registries and our own checks. JSON · Markdown
Why it's listed
- It's published in the registry under luneresearch.com, a namespace the registry only gives to whoever proves they control that domain.
Being indexed says nothing about quality, and nobody can pay for it. Is this yours? Ask for a review.
Tools it lists 13 · about 13,138 tokens of context · checked 19 hours ago
| Tool | What it does | Hint |
|---|---|---|
search_papersSearch papers | withheld | read-only |
search_papers_manySearch papers (multi-query) | withheld | read-only |
get_paper_fulltextGet paper full text | withheld | read-only |
get_paper_citationsGet paper citations | withheld | read-only |
list_conferencesList conferences | withheld | read-only |
get_conference_papersGet conference papers | withheld | read-only |
search_related_papersSearch related papers | withheld | read-only |
extract_from_papersExtract structured fields from papers | withheld | read-only |
verify_claimsVerify claims against the corpus | withheld | read-only |
gather_evidenceGather evidence and judge sufficiency | withheld | read-only |
search_research_guidanceSearch research guidance | withheld | read-only |
get_research_guidance_docGet research guidance document | withheld | read-only |
send_feedbackSend feedback to Lune | withheld | writes |
What https://mcp.luneresearch.com answered to tools/list, asked without credentials over MCP 2026-07-28. The token figure is the size of the list as sent, divided by four; a model sees about that much before it calls anything. Full definitions, input schemas included, are in the listing's JSON under mcpTools.
How its tools read to an agent 1 error · 11 warnings · 1 note
Its tool definitions contain text aimed at the model (TC19), which is how tool poisoning is written, so this site doesn't repeat them. An agent shouldn't connect to it without its user's say-so.
- errorTC19search_papersthe definition tells the model to keep something from the user
- warnTC10gather_evidence"max_iterations" is required and has a default
- warnTC10search_papers_many"limit" is required and has a default
- warnTC10search_papers_many"detail" is required and has a default
- warnTC11gather_evidence3 parameters without a description: year, year_max, year_min
- warnTC11search_papers2 parameters without a description: limit, year
- warnTC11search_related_papers1 parameter without a description: limit
- warnTC11search_research_guidancenone of its 2 parameters has a description
- warnTC14list_conferencesallowed values are in the description, not an enum: category
- warnTC22gather_evidencethe definition is about 1,816 tokens
- warnTC22search_papersthe definition is about 2,167 tokens
- warnTC22search_papers_manythe definition is about 2,272 tokens
- noteTC24server1 of 13 tools have no outputSchema
The checks from /check and anchor check, run each day on the list above: about 13,138 tokens of definitions. Not part of the score yet. Check your own server.